Welcome to the Image-Classification part, we have implemented the image-classification train pipeline based on mmdetection.
Following models are implemented using PyTorch.
- ResNet (1512.03385)
- ResNeXt (1611.05431)
- SENet (1709.01507)
- Res2Net (1904.01169)
- RegNet (/2003.13678)
To do list:
- VGG
- GoogleNet
- MobileNet
- EfficientNet
- Xception
Please see GETTING_STARTED.md for the basic usage of MMDetection.
For image-classificatin, you need to prepare your datasets in the following formate. If your folder structure is different, you may need to change the corresponding paths in config files.
hymenoptera_data/
├── train
│ ├── ants
│ └── bees
├── val
│ ├── ants
│ └── bees
python tools/train.py ${CONFIG_FILE}If you want to specify the working directory in the command, you can add an argument --work_dir ${YOUR_WORK_DIR}.
./tools/dist_train.sh ${CONFIG_FILE} ${GPU_NUM} [optional arguments]You can use the following commands to test a dataset.
# single-gpu testing
python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [--out ${RESULT_FILE}] [--eval ${EVAL_METRICS}] [--show]
# multi-gpu testing
./tools/dist_test.sh ${CONFIG_FILE} ${CHECKPOINT_FILE} ${GPU_NUM} [--out ${RESULT_FILE}] [--eval ${EVAL_METRICS}]